# Prediction of Cover–Subsidence Sinkhole Volume Using Fibre Bragg Grating Strain Sensor Data

## TL;DR

This paper explores using fiber Bragg grating sensors and machine learning to predict sinkhole volume, finding that eXtreme Gradient Boosting performs best.

## Contribution

The study introduces eXtreme Gradient Boosting as a novel and effective method for predicting sinkhole volume from sensor strain data.

## Key findings

- eXtreme Gradient Boosting achieved the highest R2 values (1.00 for training, 0.97 for testing) for volume prediction.
- Weighted Least Squares regression performed the worst with the lowest R2 values.
- eXtreme Gradient Boosting also had the lowest root mean squared errors compared to other methods.

## Abstract

Sinkholes are geohazards that commonly form in karstifiable terrain and are an ever-present danger to infrastructure and human life. This paper aims to answer the question: Can a cover–subsidence sinkhole’s volume be determined using fibre Bragg grating sensor strain data and machine-learning techniques? Exploratory data analysis was conducted on fibre Bragg grating sensor strain data collected from an experimental test rig whereby a cover–subsidence sinkhole was formed. It was found that statistical techniques and machine-learning algorithms that assume normality are inappropriate when performing phase classification and volume regression tasks on the cover–subsidence sinkhole when given fibre Bragg grating sensor’s strain data. Weighted Least Squares regression, Support Vector Regression, and eXtreme Gradient Boosting were implemented on the data during phase two of the cover–subsidence sinkhole formation to determine the volume of the sinkhole. Weighted Least Squares regression obtained the lowest R2 values for training and testing. Support Vector Regression had significantly improved results over Weighted Least Squares regression, while eXtreme Gradient Boosting obtained the highest R2 values for training and testing. The highest R2 values for eXtreme Gradient Boosting obtained were 1.00 for training and 0.97 for testing. In addition, eXtreme Gradient Boosting had the lowest root mean squared errors compared to Weighted Least Squares regression and Support Vector Regression. It was found that eXtreme Gradient Boosting is a strong candidate for determining the volume of the C–S sinkhole when using fibre Bragg grating strain data.